Zobrazeno 1 - 10
of 999
pro vyhledávání: '"Zheng, Qinghua"'
Collecting well-matched multimedia datasets is crucial for training cross-modal retrieval models. However, in real-world scenarios, massive multimodal data are harvested from the Internet, which inevitably contains Partially Mismatched Pairs (PMPs).
Externí odkaz:
http://arxiv.org/abs/2403.05105
We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome it by reducing reliance on graph structure. Even though distilling graph knowledge to s
Externí odkaz:
http://arxiv.org/abs/2403.01079
Autor:
Dang, Zhuohang, Luo, Minnan, Jia, Chengyou, Dai, Guang, Wang, Jihong, Chang, Xiaojun, Wang, Jingdong, Zheng, Qinghua
Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the informa
Externí odkaz:
http://arxiv.org/abs/2311.01686
New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data with the aid of limited labeled data containing only known intents. Without considering structure relationships between samples, previous methods generate noi
Externí odkaz:
http://arxiv.org/abs/2310.15836
Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on instance-level disc
Externí odkaz:
http://arxiv.org/abs/2310.10151
Autor:
Zhang, Zhihao, Chen, Yiwei, Zhang, Weizhan, Yan, Caixia, Zheng, Qinghua, Wang, Qi, Chen, Wangdu
Viewport prediction is a crucial aspect of tile-based 360 video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, l
Externí odkaz:
http://arxiv.org/abs/2309.14704
Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc. Current s
Externí odkaz:
http://arxiv.org/abs/2307.14605
Autor:
Cai, Zijian, Tan, Zhaoxuan, Lei, Zhenyu, Zhu, Zifeng, Wang, Hongrui, Zheng, Qinghua, Luo, Minnan
As malicious actors employ increasingly advanced and widespread bots to disseminate misinformation and manipulate public opinion, the detection of Twitter bots has become a crucial task. Though graph-based Twitter bot detection methods achieve state-
Externí odkaz:
http://arxiv.org/abs/2306.17408
Twitter bot detection has become an increasingly important and challenging task to combat online misinformation, facilitate social content moderation, and safeguard the integrity of social platforms. Though existing graph-based Twitter bot detection
Externí odkaz:
http://arxiv.org/abs/2306.12870
Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although deep learning (DL) based CER approaches have achieved excellent performance, existing cross-modal feature fusion methods used in these DL
Externí odkaz:
http://arxiv.org/abs/2306.17799